Intelligence

Visual Search

Multimodal visual document search using pgvector cosine similarity.

Searches only image-embedded chunks (chunk_index < 0) to find visually similar document pages. Text queries work because text and image embeddings share the same 768D vector space via Gemini Embedding 2.

post/api/v1/intelligence/visual-search

Request

  • Base URL: https://api.casaintelligence.com.au (the document declares no server; this is the origin it was published from)
  • URL: https://api.casaintelligence.com.au/api/v1/intelligence/visual-search
  • Auth: HTTP bearer

Request body

querystring required

Natural language search query

lgastring nullable

Filter by LGA

document_typestring nullable

Filter by document type

limitinteger

Max results to return

Response

Successful Response

total_countinteger
querystring

Changes

No recorded changes to this operation across all 1 revision of this API.